You are here

Example-guided image editing

This thesis addresses three main topics from the domain of image processing, i.e. color transfer, high-dynamic-range (HDR) imaging and guidance-based image filtering.
The first part of this thesis is dedicated to color transfer between input and target images. We adopt cluster-based techniques and apply Gaussian mixture models to carry out a more precise color transfer. In addition, we propose four new mapping policies to robustly portray the target style in terms of two key features: color, and light. Furthermore, we exploit the properties of the multivariate generalized Gaussian distributions (MGGD). in order to transfer an ensemble of features between images simultaneously. The multi-feature transfer is carried out using our novel transformation of the MGGD. Despite the efficiency of the proposed MGGD transformation for multi-feature transfer, our experiments have shown that the bounded Beta distribution provides a much more precise model for the color and light distributions of images. To exploit this property of the Beta distribution, we propose a new color transfer method, where we model the color and light distributions by the Beta distribution and introduce a novel transformation of the Beta distribution.

The second part of this thesis focuses on HDR imaging. We introduce a method for automatic creation of HDR images from only two images - flash and non-flash images. We mimic the camera response function by a brightness function and we recover details from the flash image using our new chromatic adaptation transform (CAT), called bi-local CAT. That way, we efficiently recover the dynamic range of the real-world scenes without compromising the quality of the HDR image (as our method is robust to misalignment). In the context of the HDR image creation, the bi-local CAT recovers details from the flash image, removes flash shadows and reflections.

In the last part of this thesis, we exploit the potential of the bi-local CAT for various image editing applications such as image de-noising, image de-blurring, texture transfer, etc. We propose a novel guidance-based filter in which we embed the bi-local CAT. The proposed filter performs as good as (and for certain applications even better than) state-of-the art methods.


Hristina HRISTOVA (FRVSense)
Friday, 20. October 2017 - 9:30 to 11:00
IRISA-Inria salle Métivier- campus de Beaulieu RENNES
Defense Type: 
Composition of jury: 
  • Joëlle THOLLOT Professeur à Univ. de Grenoble /rapporteur
  • Alan CHALMERS Professor à Univ. de Warwick /rapporteur
  • Marcelo BERTALMÍO Associate professor à Univ. Pompeu Fabra /examinateur
  • Nicolas BONNEEL Chargé de Chercheur CNRS, LIRIS /examinateur
  • Eric MARCHAND Professeur ESIR /examinateur
  • Kadi BOUATOUCH Professeur à Univ. de Rennes 1 /examinateur
  • Rémi COZOT Maître de Conférences à Univ. de Rennes 1 /directeur de thèse
  • Olivier LE MEUR Maître de Conférences à Univ. de Rennes 1 /co-directeur de thèse